arXiv cs.CL· Selim F. Yilmaz, E. Batuhan Kaynak, Aykut Ko\c{c}, Hamdi Dibeklio\u{g}lu, Suleyman S. Kozat·· 13 小时前AI 评分26
面向100种语言的多标签情感分析：动态加权解决标签不平衡
Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
AI 导读
研究提出一个多标签情感分析框架，采用动态加权方法在训练中平衡各类别贡献，替代按类别频率设定固定权重的静态加权，并将单标签目标识别中的 focal loss 适配到多标签场景。该方法还给出以线性时间复杂度选取最大化 macro-f1 的类别专属阈值的方法，单一模型在3种语言的9项指标中7项取得 SOTA，优于 SemEval 竞赛基线及最佳方法。代码已公开，模型支持100种语言的情感分析。
正文 · 原文
Abstract:We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis framework in multi-label setting as it obeys Plutchik's wheel of emotions. We introduce a novel dynamic weighting method that balances the contribution from each class during training, unlike previous static weighting methods that assign non-changing weights based on their class frequency. Moreover, we adapt the focal loss that favors harder instances from single-label object recognition literature to our multi-label setting. Furthermore, we derive a method to choose optimal class-specific thresholds that maximize the macro-f1 score in linear time complexity. Through an extensive set of experiments, we show that our method obtains the state-of-the-art performance in 7 of 9 metrics in 3 different languages using a single model compared to the common baselines and the best-performing methods in the SemEval competition. We publicly share our code for our model, which can perform sentiment analysis in 100 languages, to facilitate further research.
| Comments: | 12 pages, 4 figures, 4 tables. Accepted version of the article published in IEEE Transactions on Neural Networks and Learning Systems |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML) |
| Cite as: | arXiv:2008.11573 [cs.LG] |
| (or arXiv:2008.11573v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2008.11573 arXiv-issued DOI via DataCite |
|
| Journal reference: | IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 331-343, Jan. 2023 |
| Related DOI: | https://doi.org/10.1109/TNNLS.2021.3094304
DOI(s) linking to related resources |
Submission history
From: Selim Firat Yilmaz [view email]
[v1]
Wed, 26 Aug 2020 14:16:02 UTC (544 KB)
[v2]
Wed, 21 Oct 2026 15:32:15 UTC (505 KB)
来源：arXiv cs.CL · arxiv.org